Refrigeration equipment energy-saving optimization method and system based on deep learning algorithm

Abstract

The invention provides a refrigeration equipment energy-saving optimization method and system based on a deep learning algorithm, and relates to the field of refrigeration energy saving, and the method comprises the steps: obtaining original data information, and carrying out the exception processing and normalization processing, and obtaining target data information; introducing an attention mechanism to construct a prediction model according to a time sequence prediction method of a long short term memory (LSTM) network, so as to output prediction information; and performing deep learning training based on the target data information to obtain a decision model, making a decision by taking the maximum refrigerating capacity of unit energy consumption as a target according to the refrigeration demand and pre-acquired meteorological prediction data, and outputting decision information to perform regulation and control optimization on the refrigeration equipment. According to the method, the timeliness of equipment regulation and control is improved, regulation and control of the refrigeration equipment can be prospective by pre-estimating the refrigeration demand quantity in advance and setting the equipment operation in advance, and the timeliness of regulation and control is improved, so that the energy consumption loss caused by regulation and control lag is reduced.

Description

Technical Field

[0001] The present application relates to the field of refrigeration energy-saving technology, and specifically to a refrigeration equipment energy-saving optimization method and system based on a deep learning algorithm. Background Art

[0002] With the continuous growth of global energy consumption, energy conservation and emission reduction have become the focus of social attention. As the main part of building energy consumption, refrigeration equipment accounts for about 40%-60% of the total building consumption throughout the year. In the hot summer, it can even reach more than 70% in some areas. Therefore, energy-saving optimization of refrigeration equipment is of great significance to reducing energy consumption.

[0003] In the related technologies, regarding the technical methods for energy-saving optimization of refrigeration equipment, there are variable frequency technologies that adjust the speed of the compressor to match the actual refrigeration demand, such as variable frequency air conditioners. This technology can automatically adjust the speed of the compressor according to the changes in indoor temperature to ensure that it continues to operate at a lower speed during operation, thereby avoiding the energy loss caused by the traditional fixed-frequency air conditioner running at a higher speed and frequent start and stop; there are also intelligent control technologies that use more sensitive integrated sensors and automation technologies to achieve real-time monitoring and rapid adjustment of the operating status of the air-conditioning system. The related technologies are mainly concentrated in two aspects: one is to reduce the energy loss caused by frequent start and stop of the equipment by controlling the compressor to run continuously at a low frequency; the other is to be sensitive to the external environment and automatically adjust it to avoid overheating or overcooling, so as to reduce unnecessary waste.

[0004] However, the relevant technologies have the following defects: (1) The existing "frequency conversion technology" mainly focuses on reducing the operating power of the compressor and ensuring low-frequency continuous operation to achieve energy saving. It mainly uses the operating power of the compressor as the control variable to achieve the energy saving goal of reducing energy consumption, but ignores the impact of changes in evaporation temperature and condensation temperature on the cooling rate during the operation of the equipment. According to the operating principle of refrigeration equipment, the cooling effect of the refrigerant has a certain nonlinear relationship with the evaporation temperature and condensation temperature. The cooling capacity produced by a unit of refrigerant is different at different temperatures, and the cooling capacity under the final unit energy consumption will also change. (2) With the widespread application of new technologies, integrated sensors and automation technologies have also been added to the control system of refrigeration equipment to achieve real-time monitoring and automatic adjustment. However, the adjustment mechanism mostly relies on fixed settings and lacks flexibility. In addition, due to the lack of prediction of future cooling demand, the regulation is usually based on the current state, resulting in a certain lag in the adjustment of the control system, which is prone to overcooling, resulting in a waste of cooling capacity and ultimately energy loss. Summary of the invention

[0005] In response to the shortcomings of the prior art, the present application provides a refrigeration equipment energy-saving optimization method and system based on a deep learning algorithm, which solves the problem of unsatisfactory refrigeration equipment control effect caused by inaccurate prediction of refrigeration demand.

[0006] To achieve the above objectives, this application is implemented through the following technical solutions:

[0007] In a first aspect, an embodiment of the present application provides a method for energy-saving optimization of refrigeration equipment based on a deep learning algorithm, and the method for energy-saving optimization of refrigeration equipment includes: obtaining historical raw data information arranged in time series, the raw data information including the refrigeration output of the refrigeration equipment, environmental meteorological data, and daily operation data of the refrigeration equipment; performing exception processing and normalization processing on the raw data information to obtain target data information; based on the target data information, according to the time series prediction method of the long short-term memory network LSTM, introducing an attention mechanism to construct a prediction model to output prediction information to predict the refrigeration demand in the future time period; performing deep learning training based on the target data information to obtain a decision model, and making a decision based on the refrigeration demand and the pre-acquired meteorological forecast data with the goal of maximizing the refrigeration capacity per unit energy consumption, and outputting decision information; according to the decision information, regulating and optimizing the refrigeration equipment, wherein the decision information is used to characterize various values ​​of the equipment operation that maximizes the output of refrigeration capacity per unit energy consumption.

[0008] In the second aspect, an embodiment of the present application provides a refrigeration equipment energy-saving optimization system based on a deep learning algorithm, and the refrigeration equipment energy-saving optimization system includes: a data acquisition module, a data processing module, a refrigeration demand prediction module, a refrigeration equipment operation decision module and a refrigeration equipment regulation and optimization module.

[0009] Specifically, the data acquisition module is used to obtain historical raw data information arranged in time series, and the raw data information includes the refrigeration output of the refrigeration equipment, environmental meteorological data, and daily operation data of the refrigeration equipment; the data processing module is used to perform exception processing and normalization processing on the raw data information to obtain target data information; the refrigeration demand prediction module is used to construct a prediction model based on the target data information and the time series prediction method of the long short-term memory network LSTM, introduce the attention mechanism to output prediction information to predict the refrigeration demand in the future time period; the refrigeration equipment operation decision module is used to perform deep learning training based on the target data information to obtain a decision model, and make decisions based on the refrigeration demand and the pre-acquired meteorological forecast data with the goal of maximizing the refrigeration capacity per unit energy consumption, and output decision information; the refrigeration equipment control and optimization module is used to control and optimize the refrigeration equipment according to the decision information, wherein the decision information is used to characterize the various values ​​of the equipment operation that maximizes the output of refrigeration capacity per unit energy consumption.

[0010] In a third aspect, an embodiment of the present application provides an electronic device, comprising: a processor, a memory, and a program stored in the memory and executable on the processor, wherein when the program is executed by the processor, the energy-saving optimization method for refrigeration equipment based on a deep learning algorithm in the aforementioned first aspect is implemented.

[0011] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, which stores a program or instruction. When the program or instruction is executed by a processor, the energy-saving optimization method for refrigeration equipment based on a deep learning algorithm in the aforementioned first aspect is implemented.

[0012] This application provides a refrigeration equipment energy-saving optimization method and system based on deep learning algorithm. Compared with the prior art, it has the following beneficial effects:

[0013] The energy-saving optimization of refrigeration equipment in this application includes two stages. In the first stage, this application predicts the refrigeration demand in a certain time period in the future based on the time series prediction method of the long short-term memory network LSTM, collects the original data information in time series, and performs exception processing and normalization processing to obtain the target data information. According to the combination of the time series prediction method and the attention mechanism, a prediction model is constructed to predict the refrigeration demand in a certain time period in the future through model analysis, and the predicted refrigeration demand is used as the basis for subsequent control decisions, so that the control is forward-looking, more timely and on-demand. In the second stage, this application performs deep learning training based on the target data information to obtain a decision model, inputs the target data information as input data into the model for autonomous learning and repeated training, and finally infers the decision information under different environmental conditions and refrigeration needs to characterize the various values ​​of the equipment operation that maximizes the output of unit energy consumption refrigeration, and make subsequent control decisions for the refrigeration equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0015] Figure 1 It is a flow chart of a refrigeration equipment energy-saving optimization method based on a deep learning algorithm provided in an embodiment of the present application;

[0016] Figure 2 yes Figure 1 An exemplary flow chart of S130;

[0017] Figure 3It is a structural schematic diagram of a refrigeration equipment energy-saving optimization system based on a deep learning algorithm provided in an embodiment of the present application;

[0018] Figure 4 It is a structural schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0019] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention are clearly and completely described. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0020] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0021] The embodiments of the present application provide a method and system for energy-saving optimization of refrigeration equipment based on a deep learning algorithm, thereby solving the problem of unsatisfactory control effect of refrigeration equipment due to inaccurate prediction of refrigeration demand.

[0022] The technical solution in the embodiment of the present application is to solve the above technical problems, and the overall idea is as follows:

[0023] With the continuous growth of global energy consumption, energy conservation and emission reduction have become the focus of social attention. As the main part of building energy consumption, refrigeration equipment accounts for about 40%-60% of the total building consumption throughout the year. In the hot summer, it can even reach more than 70% in some areas. Therefore, energy-saving optimization of refrigeration equipment is of great significance to reducing energy consumption.

[0024] In the related technologies, regarding the technical methods for energy-saving optimization of refrigeration equipment, there are variable frequency technologies that adjust the speed of the compressor to match the actual refrigeration demand, such as variable frequency air conditioners. This technology can automatically adjust the speed of the compressor according to the changes in indoor temperature to ensure that it continues to operate at a lower speed during operation, thereby avoiding the energy loss caused by the traditional fixed-frequency air conditioner running at a higher speed and frequent start and stop; there are also intelligent control technologies that use more sensitive integrated sensors and automation technologies to achieve real-time monitoring and rapid adjustment of the operating status of the air-conditioning system. The related technologies are mainly concentrated in two aspects: one is to reduce the energy loss caused by frequent start and stop of the equipment by controlling the compressor to run continuously at a low frequency; the other is to be sensitive to the external environment and automatically adjust it to avoid overheating or overcooling, so as to reduce unnecessary waste.

[0025] However, the relevant technologies have the following defects: (1) The existing "frequency conversion technology" mainly focuses on reducing the operating power of the compressor and ensuring low-frequency continuous operation to achieve energy saving. It mainly uses the operating power of the compressor as the control variable to achieve the energy saving goal of reducing energy consumption, but ignores the impact of changes in evaporation temperature and condensation temperature on the cooling rate during the operation of the equipment. According to the operating principle of refrigeration equipment, the cooling effect of the refrigerant has a certain nonlinear relationship with the evaporation temperature and condensation temperature. The cooling capacity produced by a unit of refrigerant is different at different temperatures, and the cooling capacity under the final unit energy consumption will also change. (2) With the widespread application of new technologies, integrated sensors and automation technologies have also been added to the control system of refrigeration equipment to achieve real-time monitoring and automatic adjustment. However, the adjustment mechanism mostly relies on fixed settings and lacks flexibility. In addition, due to the lack of prediction of future cooling demand, the regulation is usually based on the current state, resulting in a certain lag in the adjustment of the control system, which is prone to overcooling, resulting in a waste of cooling capacity and ultimately energy loss.

[0026] Deep learning algorithms simulate the way the human brain processes information by building multi-layer neural networks, thereby achieving feature learning and pattern recognition of data to achieve efficient task solving capabilities. It can help the model learn relevant features by training a large amount of historical data, and then make the model better adapt to the specific application environment through fine-tuning. Applying this model to refrigeration equipment can provide a decision-making basis for the automatic adjustment of refrigeration equipment to achieve more precise regulation and control, thereby saving energy.

[0027] In order to better understand the above technical solution, the above technical solution will be described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0028] The following first introduces a refrigeration equipment energy-saving optimization method based on a deep learning algorithm provided in an embodiment of the present application.

[0029] A flowchart of a refrigeration equipment energy-saving optimization method based on a deep learning algorithm provided in an embodiment of the present application is as follows: Figure 1 As shown, the refrigeration equipment energy-saving optimization method based on the deep learning algorithm may include the following steps S110-S150.

[0030] S110, obtaining historical raw data information arranged in time series, the raw data information including refrigeration output of the refrigeration equipment, environmental meteorological data, and daily operation data of the refrigeration equipment.

[0031] S120: Perform exception processing and normalization processing on the original data information to obtain target data information.

[0032] S130. Based on the target data information and the time series prediction method of the long short-term memory network (LSTM), an attention mechanism is introduced to construct a prediction model to output prediction information to predict the refrigeration demand in the future time period.

[0033] S140, deep learning training is performed based on the target data information to obtain a decision model, and a decision is made based on the cooling demand and pre-acquired meteorological forecast data with the goal of maximizing the cooling capacity per unit energy consumption, and the decision information is output.

[0034] S150. Regulating and optimizing the refrigeration equipment according to the decision information, wherein the decision information is used to characterize various values ​​of the equipment operation that maximizes the refrigeration output per unit energy consumption.

[0035] The above is a specific implementation method of a refrigeration equipment energy-saving optimization method based on a deep learning algorithm provided in an embodiment of the present application. It can be understood that the present application includes two stages for energy-saving optimization of refrigeration equipment. In the first stage, the present application predicts the refrigeration demand in a certain time period in the future based on the time series prediction method of the long short-term memory network LSTM, and collects the original data information according to the time series, and performs exception processing and normalization processing to obtain the target data information. According to the combination of the time series prediction method and the attention mechanism, a prediction model is constructed to predict the refrigeration demand in a certain time period in the future through model analysis, and the predicted refrigeration demand is used as the basis for subsequent regulatory decisions, so that the regulation is forward-looking, more timely and can achieve on-demand cooling.

[0036] Furthermore, in the second stage, the present application conducts deep learning training based on the target data information to obtain a decision model, and inputs the target data information as input data into the model for autonomous learning and repeated training, and finally infers the decision information under different environmental conditions and refrigeration requirements to characterize the various values ​​of the equipment operation that maximizes the refrigeration output per unit energy consumption, and make subsequent regulation decisions for the refrigeration equipment.

[0037] In one example, the environmental meteorological data includes the ambient temperature, ambient humidity and light intensity, and the daily operation data includes: energy consumption value, compressor operating power, evaporation temperature, condensation temperature and expansion valve operating value. It is understandable that the present application takes into account the influence of the difference between evaporation temperature and condensation temperature on the refrigeration effect, and on the basis of considering energy saving by reducing the compressor power, increases the refrigeration output per unit energy consumption by regulating the evaporation temperature and condensation temperature during the operation of the equipment, so as to improve the energy efficiency ratio and achieve energy saving.

[0038] In some embodiments, the above-mentioned abnormal processing and normalization processing are performed on the original data information to obtain the target data information, that is, the above-mentioned S120 may specifically include the following steps:

[0039] S210, marking and filling missing values ​​in the original data information by using a linear filling method;

[0040] S220, identifying outliers in the data by a box plot method, setting the outliers as null values ​​after determining the outliers, and performing linear supplementation to ensure the integrity and continuity of the data;

[0041] S230, normalize the data to ensure data consistency and obtain target data information; wherein the target data information includes target refrigeration information, target environmental information and target operation information corresponding to refrigeration output, environmental meteorological data and daily operation data respectively.

[0042] In the embodiment of the present application, it can be understood that the present application first performs data preprocessing on the acquired raw data information to complete the cleaning process; specifically, the missing values ​​can be marked and filled in by linear filling, and the box plot method is used for the identification of outliers. The interquartile range of the box plot is used to detect the outliers. After finding the outliers, the outliers are first set to null values ​​and then linearly supplemented. After ensuring the integrity and continuity of the data through the above operations, all data are normalized to ensure the consistency of the data for subsequent analysis and prediction.

[0043] In some embodiments, please refer to Figure 2 , the aforementioned method based on the target data information and the time series prediction method of the long short-term memory network LSTM is used to introduce the attention mechanism to construct a prediction model to output prediction information to predict the refrigeration demand in the future time period, that is, the aforementioned S130 may specifically include the following steps:

[0044] S310, selecting time and target environment information as characteristic variables, and determining the characteristic variables and target cooling information as input information;

[0045] S320, selecting an activation function, a loss function, and an optimization algorithm, and determining the number of LSTM units, the number of layers, and the neural network layer for output mapping to obtain an LSTM model structure;

[0046] S330, introducing an attention mechanism into the LSTM model structure by calculating the attention score or weight distribution, and obtaining a target neural network structure;

[0047] S340, training the target neural network structure based on the input information to obtain a prediction model;

[0048] S350: Output prediction information based on the prediction model to characterize the refrigeration demand in a future time period.

[0049] In the embodiment of the present application, it can be understood that the target environmental information is a factor that may affect the cooling capacity. The present application selects characteristic variables and target cooling information as input information, and can also calculate the Pearson correlation coefficient for screening; the present application first determines the preliminary LSTM model structure, and then introduces the attention mechanism, so that the model can automatically learn and pay attention to the important features in the input information, thereby highlighting the role of important features. The present application constructs a model by combining the above-mentioned time series prediction method based on the long short-term memory network LSTM with the attention mechanism, and uses historical data for training. It can predict the cooling demand in a certain time period in the future and output it as part of the input data for the next stage.

[0050] In one example, the target neural network structure is trained based on the input information to obtain a prediction model, that is, the aforementioned S340 may specifically include the following steps:

[0051] S410, inputting the input information into the target LSTM model structure;

[0052] S420, learning the long-term dependency of the time series corresponding to the input information through the iteration of time steps and the connection between LSTM units, and extracting key features;

[0053] S430: During the model training process, the prediction model is obtained by adjusting the network parameters to minimize the prediction error.

[0054] In some embodiments, the above-mentioned deep learning training is performed based on the target data information to obtain a decision model, and a decision is made based on the cooling demand and the pre-acquired meteorological forecast data with the maximum cooling capacity per unit energy consumption as the goal, and the decision information is output, that is, the above-mentioned S140 may specifically include the following steps:

[0055] S510, dividing the target data information into a test set and a validation set according to a preset ratio;

[0056] S520, input the test set into a preset deep learning framework for training to obtain an initial model;

[0057] S530, testing the initial model based on the validation set, and continuously adjusting the internal parameters of the initial model according to the obtained test results to obtain a decision model; wherein the decision model is used to determine the refrigeration output of the refrigeration equipment per unit energy consumption under different environments and different operating conditions;

[0058] S540, inputting the cooling demand and the obtained weather forecast data into the decision-making model, making a decision with the maximum cooling capacity per unit energy consumption as the goal, and outputting decision information.

[0059] In the embodiments of the present application, it can be understood that the present application constructs a decision-making model based on a deep learning algorithm to find the various operating values ​​of the refrigeration equipment that maximizes the refrigeration output per unit energy consumption, and then makes a decision based on the prediction results of the previous stage to determine the operating values ​​of the refrigeration equipment that maximizes the refrigeration output per unit energy consumption.

[0060] It should be noted that since the target data information includes target refrigeration information, target environmental information and target operation information corresponding to the refrigeration output, environmental meteorological data and daily operation data respectively, in the process of inputting the test set into the deep learning framework for training, the model can learn the relationship between the refrigeration capacity, environmental meteorological data and daily operation data of the refrigeration equipment, so that after determining the decision model, based on the refrigeration demand at future times and the obtained meteorological forecast data, the model can make decisions and output decision information.

[0061] In one example, the refrigeration equipment is regulated and optimized according to the decision information, that is, the aforementioned S150 includes: determining the subsequent operation plan of the refrigeration equipment for regulation and optimization according to the decision information; wherein the subsequent operation plan includes the equipment start-up time, the initial operating power of the compressor, the initial opening of the expansion valve, the cooling water circulation flow rate and the air-conditioning fan speed.

[0062] In some embodiments, the present application provides a refrigeration equipment energy-saving optimization system 600 based on a deep learning algorithm, such as Figure 3 As shown, the refrigeration equipment energy-saving optimization system 600 may include the following modules:

[0063] The data acquisition module 610 is used to acquire historical raw data information arranged in time series, the raw data information including the refrigeration output of the refrigeration equipment, environmental meteorological data, and daily operation data of the refrigeration equipment;

[0064] The data processing module 620 is used to perform abnormal processing and normalization processing on the original data information to obtain the target data information;

[0065] The cooling demand prediction module 630 is used to construct a prediction model based on the target data information and the time series prediction method of the long short-term memory network LSTM, so as to output prediction information to predict the cooling demand in the future time period;

[0066] The refrigeration equipment operation decision module 640 is used to perform deep learning training based on the target data information to obtain a decision model, and make a decision based on the refrigeration demand and pre-acquired meteorological forecast data with the goal of maximizing the refrigeration capacity per unit energy consumption, and output decision information;

[0067] The refrigeration equipment control and optimization module 650 is used to control and optimize the refrigeration equipment according to the decision information, wherein the decision information is used to characterize various values ​​of the equipment operation that maximizes the output of refrigeration per unit energy consumption.

[0068] According to an embodiment of the present application, any multiple modules among the data acquisition module 610, the data processing module 620, the refrigeration demand prediction module 630, the refrigeration equipment operation decision module 640 and the refrigeration equipment control optimization module 650 can be combined into one module for implementation, or any one of the modules can be split into multiple modules. Alternatively, at least part of the functions of one or more of these modules can be combined with at least part of the functions of other modules and implemented in one module.

[0069] In some embodiments, the data processing module 620 may be specifically used to:

[0070] Linear filling is used to mark and fill missing values ​​in the original data information;

[0071] The outliers in the data were identified by the box plot method. After the outliers were identified, they were set as null values ​​and linear supplementation was performed to ensure the integrity and continuity of the data.

[0072] The data is normalized to ensure data consistency and obtain target data information; wherein the target data information includes target refrigeration information, target environmental information and target operation information corresponding to refrigeration output, environmental meteorological data and daily operation data respectively.

[0073] In some embodiments, the cooling demand prediction module 630 may specifically include:

[0074] A first selection and determination unit 631 is used to select time and target environment information as characteristic variables, and determine the characteristic variables and target cooling information as input information;

[0075] The second selection and determination unit 632 is used to select an activation function, a loss function and an optimization algorithm, and determine the number of LSTM units, the number of layers and the neural network layer for output mapping to obtain an LSTM model structure;

[0076] An attention introduction unit 633 is used to introduce an attention mechanism into the LSTM model structure by calculating an attention score or a weight distribution to obtain a target neural network structure;

[0077] A training unit 634 is used to train the target neural network structure based on the input information to obtain a prediction model;

[0078] The output unit 635 is used to output prediction information based on the prediction model to represent the cooling demand in the future time period.

[0079] In some embodiments, the training unit 634 may be specifically configured to:

[0080] Input the input information to the target LSTM model structure;

[0081] Through the iteration of time steps and the connection between LSTM units, the long-term dependencies of the time series corresponding to the input information are learned and key features are extracted;

[0082] During the model training process, the prediction model is obtained by adjusting the network parameters to minimize the prediction error.

[0083] In some embodiments, the refrigeration equipment operation decision module 640 may be specifically used to:

[0084] Divide the target data information into a test set and a validation set according to a preset ratio;

[0085] Input the test set into the preset deep learning framework for training to obtain the initial model;

[0086] The initial model is tested based on the validation set, and the internal parameters of the initial model are continuously adjusted according to the test results to obtain a decision model; wherein the decision model is used to determine the refrigeration output of the refrigeration equipment per unit energy consumption under different environments and different operating conditions;

[0087] The cooling demand and the obtained weather forecast data are input into the decision-making model, and the decision is made with the maximum cooling capacity per unit energy consumption as the goal, and the decision information is output.

[0088] Figure 3 Each module in the system shown has the function of implementing each step in the aforementioned refrigeration equipment energy-saving optimization method based on deep learning algorithm, and can achieve its corresponding technical effect. For the sake of concise description, it will not be repeated here.

[0089] In some embodiments, the present application provides an electronic device, the structure diagram of the electronic device is as follows Figure 4 shown.

[0090] The electronic device may include a processor 710 and a memory 720 storing computer program instructions.

[0091] Specifically, the processor 710 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application.

[0092] The memory 720 may include a large capacity memory for data or instructions. By way of example and not limitation, the memory 720 may include a hard disk drive (HDD), a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive or a combination of two or more of these. In appropriate cases, the memory 720 may include a removable or non-removable (or fixed) medium. In appropriate cases, the memory 720 may be inside or outside the integrated gateway disaster recovery device. In a specific embodiment, the memory 720 is a non-volatile solid-state memory.

[0093] The memory 720 may include a read-only memory (ROM), a random access memory (RAM), a disk storage medium device, an optical storage medium device, a flash memory device, an electrical, optical or other physical / tangible memory storage device. Therefore, generally, the memory 720 includes one or more tangible (non-transitory) computer-readable storage media (e.g., a memory device) encoded with software including computer executable instructions, and when the software is executed (e.g., by one or more processors), it can perform the operations described in any of the above-mentioned embodiments of the method for energy-saving optimization of refrigeration equipment based on a deep learning algorithm.

[0094] The processor 710 reads and executes computer program instructions stored in the memory 720 to implement any one of the refrigeration equipment energy-saving optimization methods based on the deep learning algorithm in the above embodiments.

[0095] In one example, the electronic device may further include a communication interface 730 and a bus 700. Figure 4 As shown, the processor 710, the memory 720, and the communication interface 730 are connected via a bus 700 and communicate with each other.

[0096] The communication interface 730 is mainly used to implement communication between various modules, devices, units and / or equipment in the embodiments of the present application.

[0097] Bus 700 includes hardware, software or both, and the parts of online data flow billing equipment are coupled to each other. For example, but not limitation, bus may include accelerated graphics port (AGP) or other graphics bus, enhanced industrial standard architecture (EISA) bus, front-end bus (FSB), hypertransport (HT) interconnection, industrial standard architecture (ISA) bus, infinite bandwidth interconnection, low pin count (LPC) bus, memory bus, micro channel architecture (MCA) bus, peripheral component interconnection (PCI) bus, PCI-Express (PCI-X) bus, serial advanced technology attachment (SATA) bus, video electronics standard association local (VLB) bus or other suitable bus or two or more of these combinations. In appropriate cases, bus 700 may include one or more buses. Although the present application embodiment describes and shows a specific bus, the present application considers any suitable bus or interconnection.

[0098] In addition, in combination with the refrigeration equipment energy-saving optimization method based on deep learning algorithm in the above embodiment, the embodiment of the present application can provide a computer storage medium for implementation. The computer storage medium stores computer program instructions; when the computer program instructions are executed by the processor, any one of the refrigeration equipment energy-saving optimization methods based on deep learning algorithm in the above embodiment is implemented.

[0099] It should be clear that the present application is not limited to the specific configuration and processing described above and shown in the figures. For the sake of simplicity, a detailed description of the known method is omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of the present application is not limited to the specific steps described and shown, and those skilled in the art can make various changes, modifications and additions, or change the order between the steps after understanding the spirit of the present application.

[0100] The functional blocks shown in the above block diagram can be implemented as hardware, software, firmware or a combination thereof. When implemented in hardware, it can be, for example, an electronic circuit, an application specific integrated circuit (ASIC), appropriate firmware, a plug-in, a function card, etc. When implemented in software, the elements of the present application are programs or code segments that are used to perform the required tasks. The program or code segment can be stored in a machine-readable medium, or transmitted on a transmission medium or a communication link by a data signal carried in a carrier wave. "Machine-readable medium" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, optical fiber media, radio frequency (RF) links, etc. The code segment can be downloaded via a computer network such as the Internet, an intranet, etc.

[0101] It should also be noted that the exemplary embodiments mentioned in this application describe some methods or systems based on a series of steps or devices. However, this application is not limited to the order of the above steps, that is, the steps can be performed in the order mentioned in the embodiment, or in a different order from the embodiment, or several steps can be performed simultaneously.

[0102] Aspects of the present disclosure are described above with reference to the flowchart and / or block diagram of the method, device (system) and computer program product according to the embodiment of the present disclosure. It should be understood that each box in the flowchart and / or block diagram and the combination of each box in the flowchart and / or block diagram can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer or other programmable data processing device to produce a machine so that these instructions executed by the processor of the computer or other programmable data processing device enable the implementation of the function / action specified in one or more boxes of the flowchart and / or block diagram. It can also be understood that each box in the block diagram and / or flowchart and the combination of boxes in the block diagram and / or flowchart can also be implemented by special-purpose hardware that performs the specified function or action, or can be implemented by a combination of special-purpose hardware and computer instructions.

[0103] In summary, compared with the prior art, this application has the following beneficial effects:

[0104] 1. This application combines the time series prediction method based on the long short-term memory network with the attention mechanism to construct a prediction model to predict the refrigeration demand in a certain time period in the future through model analysis, thereby improving the accuracy of the cooling capacity prediction, thereby providing more accurate data support for the regulation of the equipment and improving the accuracy of its regulation; making the regulation forward-looking, more timely and achieving on-demand cooling.

[0105] 2. This application conducts deep learning training based on target data information to obtain a decision-making model, and inputs the target data information as input data into the model for autonomous learning and repeated training, and finally infers the decision information under different environmental conditions and refrigeration requirements, finds the optimal equipment operation value, and then adjusts the equipment operation settings to increase the refrigeration output per unit energy consumption, thereby improving the energy efficiency ratio of the refrigeration equipment and achieving energy saving.

[0106] 3. This application improves the timeliness of equipment regulation. By predicting the refrigeration demand in advance and setting the equipment operation in advance, the regulation of the refrigeration equipment can be forward-looking, improving the timeliness of regulation, thereby reducing energy consumption losses caused by delayed regulation.

[0107] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A refrigeration equipment energy-saving optimization method based on deep learning algorithm, characterized in that: include: Acquire historical raw data information arranged in time series, the raw data information including refrigeration output of the refrigeration equipment, environmental meteorological data, and daily operation data of the refrigeration equipment; Performing abnormal processing and normalization processing on the original data information to obtain target data information; Based on the target data information, according to the time series prediction method of the long short-term memory network LSTM, an attention mechanism is introduced to construct a prediction model to output prediction information to predict the refrigeration demand in the future time period; Based on the target data information, deep learning training is performed to obtain a decision model, and according to the refrigeration demand and pre-acquired meteorological forecast data, a decision is made with the maximum refrigeration capacity per unit energy consumption as the goal, and decision information is output; The refrigeration equipment is regulated and optimized according to the decision information, wherein the decision information is used to characterize various values ​​of equipment operation that maximize the output of refrigeration per unit energy consumption.

2. The refrigeration equipment energy-saving optimization method based on deep learning algorithm according to claim 1, characterized in that: The environmental meteorological data include environmental temperature, environmental humidity and light intensity, and the daily operation data include: energy consumption value, compressor operating power, evaporation temperature, condensation temperature and expansion valve operating value.

3. The refrigeration equipment energy-saving optimization method based on deep learning algorithm according to claim 1, characterized in that: The performing of abnormal processing and normalization processing on the original data information to obtain target data information includes: Marking and filling missing values ​​in the original data information by using a linear filling method; The outliers in the data were identified by the box plot method. After the outliers were identified, they were set as null values ​​and linear supplementation was performed to ensure the integrity and continuity of the data. Normalize the data to ensure data consistency and obtain target data information; The target data information includes target refrigeration information, target environment information and target operation information corresponding to the refrigeration output, the environmental meteorological data and the daily operation data respectively.

4. The refrigeration equipment energy-saving optimization method based on deep learning algorithm according to claim 3, characterized in that: Based on the target data information, according to the time series prediction method of the long short-term memory network LSTM, an attention mechanism is introduced to construct a prediction model to output prediction information to predict the refrigeration demand in the future time period, including: Selecting time and the target environment information as characteristic variables, and determining the characteristic variables and the target cooling information as input information; Select the activation function, loss function, and optimization algorithm, and determine the number of LSTM units, the number of layers, and the neural network layer for output mapping to obtain the LSTM model structure; By calculating the attention score or weight distribution, an attention mechanism is introduced into the LSTM model structure to obtain a target neural network structure; Training the target neural network structure based on the input information to obtain a prediction model; Outputting prediction information based on the prediction model to represent the refrigeration demand in a future time period.

5. The refrigeration equipment energy-saving optimization method based on deep learning algorithm according to claim 4, characterized in that: The step of training the target neural network structure based on the input information to obtain a prediction model includes: Inputting the input information into the target LSTM model structure; Learning the long-term dependency of the time series corresponding to the input information through iteration of time steps and connections between the LSTM units, and extracting key features; During the model training process, the prediction model is obtained by adjusting the network parameters to minimize the prediction error.

6. The refrigeration equipment energy-saving optimization method based on deep learning algorithm according to claim 3, characterized in that: The deep learning training is performed based on the target data information to obtain a decision model, and a decision is made based on the cooling demand and the pre-acquired meteorological forecast data with the maximum cooling capacity per unit energy consumption as the goal, and the decision information is output, including: Dividing the target data information into a test set and a validation set according to a preset ratio; Input the test set into a preset deep learning framework for training to obtain an initial model; The initial model is tested based on the validation set, and the internal parameters of the initial model are continuously adjusted according to the test results to obtain a decision model; wherein the decision model is used to determine the refrigeration output of the refrigeration equipment per unit energy consumption under different environments and different operating conditions; The refrigeration demand and the acquired meteorological forecast data are input into the decision model, a decision is made with the maximum refrigeration capacity per unit energy consumption as the goal, and decision information is output.

7. The refrigeration equipment energy-saving optimization method based on deep learning algorithm according to claim 1, characterized in that: The step of optimizing the refrigeration equipment according to the decision information includes: Based on the decision information, a subsequent operation plan of the refrigeration equipment is determined for control optimization; wherein the subsequent operation plan includes equipment startup time, initial operating power of the compressor, initial opening of the expansion valve, cooling water circulation flow rate and air conditioning fan speed.

8. A refrigeration equipment energy-saving optimization system based on deep learning algorithm, characterized in that: include: A data acquisition module, used to acquire historical raw data information arranged in time series, wherein the raw data information includes refrigeration output of the refrigeration equipment, environmental meteorological data, and daily operation data of the refrigeration equipment; A data processing module is used to perform abnormal processing and normalization processing on the original data information to obtain target data information; A refrigeration demand prediction module is used to construct a prediction model based on the target data information and the time series prediction method of the long short-term memory network LSTM, so as to output prediction information to predict the refrigeration demand in the future time period; A refrigeration equipment operation decision module is used to perform deep learning training based on the target data information to obtain a decision model, and make a decision based on the refrigeration demand and pre-acquired meteorological forecast data with the goal of maximizing the refrigeration capacity per unit energy consumption, and output decision information; The refrigeration equipment control and optimization module is used to control and optimize the refrigeration equipment according to the decision information, wherein the decision information is used to characterize various values ​​of equipment operation that maximizes the output of refrigeration per unit energy consumption.

9. An electronic device, characterized in that: include: A processor, a memory, and a program stored in the memory and executable on the processor, wherein when the program is executed by the processor, the method for energy-saving optimization of refrigeration equipment based on a deep learning algorithm as described in any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores programs or instructions, and when the programs or instructions are executed by the processor, the energy-saving optimization method for refrigeration equipment based on the deep learning algorithm as described in any one of claims 1 to 7 is implemented.

Images